View in EDS HTML Full Text PDF Full Text

SPEQTACLE: An automated generalized fuzzy C-means algorithm for tumor delineation in PET.

Saved in:
Bibliographic Details
Title: SPEQTACLE: An automated generalized fuzzy C-means algorithm for tumor delineation in PET.
Authors: Lapuyade‐Lahorgue, Jérôme1, Visvikis, Dimitris1, Pradier, Olivier2, Cheze Le Rest, Catherine3, Hatt, Mathieu1
Source: Medical Physics. Oct2015, Vol. 42 Issue 10, p5720-5734. 15p.
Subjects: Fuzzy algorithms, Positron emission tomography, Cancer tomography, Estimation theory, Bayesian analysis, Parameters (Statistics)
Abstract: Purpose: Accurate tumor delineation in positron emission tomography (PET) images is crucial in oncology. Although recent methods achieved good results, there is still room for improvement regarding tumors with complex shapes, low signal-to-noise ratio, and high levels of uptake heterogeneity. Methods: The authors developed and evaluated an original clustering-based method called spatial positron emission quantification of tumor--Automatic Lp-norm estimation (SPEQTACLE), based on the fuzzy C-means (FCM) algorithm with a generalization exploiting a Hilbertian norm to more accurately account for the fuzzy and non-Gaussian distributions of PET images. An automatic and reproducible estimation scheme of the norm on an image-by-image basis was developed. Robustness was assessed by studying the consistency of results obtained on multiple acquisitions of the NEMA phantom on three different scanners with varying acquisition parameters. Accuracy was evaluated using classification errors (CEs) on simulated and clinical images. SPEQTACLE was compared to another FCM implementation, fuzzy local information C-means (FLICM) and fuzzy locally adaptive Bayesian (FLAB). Results: SPEQTACLE demonstrated a level of robustness similar to FLAB (variability of 14%±9% vs 14%±7%, p = 0.15) and higher than FLICM (45%±18%, p < 0.0001), and improved accuracy with lower CE (14%±11%) over both FLICM (29%±29%) and FLAB (22%±20%) on simulated images. Improvement was significant for the more challenging cases with CE of 17%±11% for SPEQTACLE vs 28%±22% for FLAB (p = 0.009) and 40%±35% for FLICM (p < 0.0001). For the clinical cases, SPEQTACLE outperformed FLAB and FLICM (15%±6% vs 37%±14% and 30%±17%, p < 0.004). Conclusions: SPEQTACLE benefitted from the fully automatic estimation of the norm on a case-by-case basis. This promising approach will be extended to multimodal images and multiclass estimation in future developments. [ABSTRACT FROM AUTHOR]
Copyright of Medical Physics is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: egs
DbLabel: Engineering Source
An: 110199893
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: SPEQTACLE: An automated generalized fuzzy C-means algorithm for tumor delineation in PET.
– Name: Author
  Label: Authors
  Group: Au
  Data: &lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Lapuyade‐Lahorgue%2C+J&#233;r&#244;me%22&quot;&gt;Lapuyade‐Lahorgue, J&#233;r&#244;me&lt;/searchLink&gt;&lt;relatesTo&gt;1&lt;/relatesTo&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Visvikis%2C+Dimitris%22&quot;&gt;Visvikis, Dimitris&lt;/searchLink&gt;&lt;relatesTo&gt;1&lt;/relatesTo&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Pradier%2C+Olivier%22&quot;&gt;Pradier, Olivier&lt;/searchLink&gt;&lt;relatesTo&gt;2&lt;/relatesTo&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Cheze+Le+Rest%2C+Catherine%22&quot;&gt;Cheze Le Rest, Catherine&lt;/searchLink&gt;&lt;relatesTo&gt;3&lt;/relatesTo&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Hatt%2C+Mathieu%22&quot;&gt;Hatt, Mathieu&lt;/searchLink&gt;&lt;relatesTo&gt;1&lt;/relatesTo&gt;
– Name: TitleSource
  Label: Source
  Group: Src
  Data: &lt;searchLink fieldCode=&quot;JN&quot; term=&quot;%22Medical+Physics%22&quot;&gt;Medical Physics&lt;/searchLink&gt;. Oct2015, Vol. 42 Issue 10, p5720-5734. 15p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: &lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Fuzzy+algorithms%22&quot;&gt;Fuzzy algorithms&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Positron+emission+tomography%22&quot;&gt;Positron emission tomography&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Cancer+tomography%22&quot;&gt;Cancer tomography&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Estimation+theory%22&quot;&gt;Estimation theory&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Bayesian+analysis%22&quot;&gt;Bayesian analysis&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Parameters+%28Statistics%29%22&quot;&gt;Parameters (Statistics)&lt;/searchLink&gt;
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Purpose: Accurate tumor delineation in positron emission tomography (PET) images is crucial in oncology. Although recent methods achieved good results, there is still room for improvement regarding tumors with complex shapes, low signal-to-noise ratio, and high levels of uptake heterogeneity. Methods: The authors developed and evaluated an original clustering-based method called spatial positron emission quantification of tumor--Automatic Lp-norm estimation (SPEQTACLE), based on the fuzzy C-means (FCM) algorithm with a generalization exploiting a Hilbertian norm to more accurately account for the fuzzy and non-Gaussian distributions of PET images. An automatic and reproducible estimation scheme of the norm on an image-by-image basis was developed. Robustness was assessed by studying the consistency of results obtained on multiple acquisitions of the NEMA phantom on three different scanners with varying acquisition parameters. Accuracy was evaluated using classification errors (CEs) on simulated and clinical images. SPEQTACLE was compared to another FCM implementation, fuzzy local information C-means (FLICM) and fuzzy locally adaptive Bayesian (FLAB). Results: SPEQTACLE demonstrated a level of robustness similar to FLAB (variability of 14%&#177;9% vs 14%&#177;7%, p = 0.15) and higher than FLICM (45%&#177;18%, p &lt; 0.0001), and improved accuracy with lower CE (14%&#177;11%) over both FLICM (29%&#177;29%) and FLAB (22%&#177;20%) on simulated images. Improvement was significant for the more challenging cases with CE of 17%&#177;11% for SPEQTACLE vs 28%&#177;22% for FLAB (p = 0.009) and 40%&#177;35% for FLICM (p &lt; 0.0001). For the clinical cases, SPEQTACLE outperformed FLAB and FLICM (15%&#177;6% vs 37%&#177;14% and 30%&#177;17%, p &lt; 0.004). Conclusions: SPEQTACLE benefitted from the fully automatic estimation of the norm on a case-by-case basis. This promising approach will be extended to multimodal images and multiclass estimation in future developments. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: &lt;i&gt;Copyright of Medical Physics is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder&#39;s express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.&lt;/i&gt; (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=110199893
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1118/1.4929561
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 15
        StartPage: 5720
    Subjects:
      – SubjectFull: Fuzzy algorithms
        Type: general
      – SubjectFull: Positron emission tomography
        Type: general
      – SubjectFull: Cancer tomography
        Type: general
      – SubjectFull: Estimation theory
        Type: general
      – SubjectFull: Bayesian analysis
        Type: general
      – SubjectFull: Parameters (Statistics)
        Type: general
    Titles:
      – TitleFull: SPEQTACLE: An automated generalized fuzzy C-means algorithm for tumor delineation in PET.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Lapuyade‐Lahorgue, Jérôme
      – PersonEntity:
          Name:
            NameFull: Visvikis, Dimitris
      – PersonEntity:
          Name:
            NameFull: Pradier, Olivier
      – PersonEntity:
          Name:
            NameFull: Cheze Le Rest, Catherine
      – PersonEntity:
          Name:
            NameFull: Hatt, Mathieu
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 10
              Text: Oct2015
              Type: published
              Y: 2015
          Identifiers:
            – Type: issn-print
              Value: 00942405
          Numbering:
            – Type: volume
              Value: 42
            – Type: issue
              Value: 10
          Titles:
            – TitleFull: Medical Physics
              Type: main
ResultId 1